© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 11615
    Prev
    Next
    INDEX
    Explanations

    html code including tags and attributes, particularly related to web navigation, plugin versions, and maven repository structure

    oai_token-act-pair · gemini-2.0-flash

    </

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Normdatei
    -0.95
    CloseOperation
    -0.79
    rrggbb
    -0.73
    ymus
    -0.69
    utnik
    -0.67
    writeFieldEnd
    -0.67
     ProtoMessage
    -0.66
     ویکی‌پدی
    -0.66
    JspWriter
    -0.65
    principalTable
    -0.64
    POSITIVE LOGITS
     en
    0.51
     corred
    0.44
    浪
    0.43
    Tē
    0.42
    -
    0.41
     agrade
    0.40
    pak
    0.40
     sopr
    0.40
    klar
    0.39
     repente
    0.39
    Activations Density 7.174%

    No Known Activations